17 March 2017 CS-BoW: a scalable parallel image recognition method
Author Affiliations +
Proceedings Volume 10341, Ninth International Conference on Machine Vision (ICMV 2016); 103410M (2017) https://doi.org/10.1117/12.2268411
Event: Ninth International Conference on Machine Vision, 2016, Nice, France
In this paper, a scalable parallel image recognition method, CS-BoW (Class-Specific Bag of Words), is proposed. CSBoW builds submodels for each class using weighted BoW in training phase. In test phase, CS-BoW calculates and sorts the coding residual for every class of each test image, then each test image is assigned to the class which has the smallest coding residual. The proposed CS-BoW is easy to be scaled, the only thing to do to extend training dataset with a new class is to build a submodel for the new class. No extra calculation for existing data. CS-BoW calculates coding residual of each test image for every class, so it is convenient to obtain Top N accuracy, while many other image recognition methods can only release Top 1 accuracy. The experimental results show that CS-BoW achieves comparable accuracy in very short time if it is run parallelly, it can be as fast as 0.05s per image in caltech 101 and caltech 256.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yang Liu, Yang Liu, } "CS-BoW: a scalable parallel image recognition method", Proc. SPIE 10341, Ninth International Conference on Machine Vision (ICMV 2016), 103410M (17 March 2017); doi: 10.1117/12.2268411; https://doi.org/10.1117/12.2268411


Parallel Algorithms For Real-Time Vision
Proceedings of SPIE (April 30 1987)
Scene understanding based on network-symbolic models
Proceedings of SPIE (May 25 2005)
Grouping-based recognition system
Proceedings of SPIE (February 01 1992)

Back to Top